{"url":"/task/unsupervised-text-classification","name":"Unsupervised Text Classification","slug":"unsupervised-text-classification","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":12,"papers_with_code":5,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-text-classification-on-1","slug":"unsupervised-text-classification-on-1","dataset":"20NewsGroups","dataset_url":"/dataset/20newsgroups","rows_in_archive":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Lbl2Vec","paper_title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","paper_url":"/paper/lbl2vec-an-embedding-based-approach-for","paper_date":"2022-10-12","arxiv_id":"2210.06023","code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-text-classification-on-ag-news","slug":"unsupervised-text-classification-on-ag-news","dataset":"AG News","dataset_url":"/dataset/ag-news","rows_in_archive":2,"metrics":["F1 score","F1-score"],"first_row_in_archive_order":{"model":"Lbl2Vec","paper_title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","paper_url":"/paper/lbl2vec-an-embedding-based-approach-for","paper_date":"2022-10-12","arxiv_id":"2210.06023","code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-text-classification-on-medical","slug":"unsupervised-text-classification-on-medical","dataset":"Medical Abstracts","dataset_url":"/dataset/medical-abstracts","rows_in_archive":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Lbl2TransformerVec","paper_title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","paper_url":"/paper/evaluating-unsupervised-text-classification","paper_date":"2022-11-29","arxiv_id":"2211.16285","code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"},{"title":"sebischair/medical-abstracts-tc-corpus","url":"https://github.com/sebischair/medical-abstracts-tc-corpus"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-text-classification-on-yahoo","slug":"unsupervised-text-classification-on-yahoo","dataset":"Yahoo! Answers","dataset_url":"/dataset/yahoo-answers","rows_in_archive":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Lbl2TransformerVec","paper_title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","paper_url":"/paper/evaluating-unsupervised-text-classification","paper_date":"2022-11-29","arxiv_id":"2211.16285","code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"},{"title":"sebischair/medical-abstracts-tc-corpus","url":"https://github.com/sebischair/medical-abstracts-tc-corpus"}],"syntology":null}}],"datasets":[{"url":"/dataset/ag-news","name":"AG News","full_name":"AG’s News Corpus","num_papers_in_archive":969},{"url":"/dataset/yahoo-answers","name":"Yahoo! Answers","full_name":"","num_papers_in_archive":132},{"url":"/dataset/20newsgroups","name":"20NewsGroups","full_name":"","num_papers_in_archive":20},{"url":"/dataset/medical-abstracts","name":"Medical Abstracts","full_name":"Medical Abstracts Text Classification Dataset","num_papers_in_archive":4}],"subtasks":[],"parent_tasks":[{"url":"/task/text-classification","name":"Text Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":5,"of":5,"tagged_in_all":12,"items":[{"url":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","arxiv_id":"2211.16285","repositories_listed":2,"syntology":null},{"url":"/paper/lbl2vec-an-embedding-based-approach-for","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","date":"2022-10-12","arxiv_id":"2210.06023","repositories_listed":1,"syntology":null},{"url":"/paper/lex2sent-a-bagging-approach-to-unsupervised-1","title":"Lex2Sent: A bagging approach to unsupervised sentiment analysis","date":"2022-09-26","arxiv_id":"2209.13023","repositories_listed":1,"syntology":null},{"url":"/paper/docscan-unsupervised-text-classification-via","title":"DocSCAN: Unsupervised Text Classification via Learning from Neighbors","date":"2021-05-09","arxiv_id":"2105.04024","repositories_listed":1,"syntology":null},{"url":"/paper/diversity-based-generalization-for-neural","title":"Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift","date":"2020-02-25","arxiv_id":"2002.10937","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}